Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4779. Min Act: -0.0000

Data Index: 38265 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4316. Min Act: -0.0000

Data Index: 695353 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4556. Min Act: -0.0000

Data Index: 107973 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4273. Min Act: -0.0000

Data Index: 386699 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4313. Min Act: -0.0000

Data Index: 400811 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1186442 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4100. Min Act: -0.0000

Data Index: 46368 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1267218 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3902. Min Act: -0.0000

Data Index: 410337 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4128. Min Act: -0.0000

Data Index: 187603 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1286641 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1114575 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3930. Min Act: -0.0000

Data Index: 576547 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3624. Min Act: -0.0000

Data Index: 502689 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3567. Min Act: -0.0000

Data Index: 585207 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3566. Min Act: -0.0000

Data Index: 335365 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3298. Min Act: -0.0000

Data Index: 739097 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3265. Min Act: -0.0000

Data Index: 872470 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1084919 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.4779. Min Range: -0.4779

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1069535 (C4 (Web Text))

Max Activating Token Index: 159